Grubbs outlier test calculator
Paste a sample and significance level. The calculator identifies the observation farthest from the mean.
Observation assessment
| Position | Value | Standardized distance | Flag |
|---|---|---|---|
| Fill in the fields above — the result is computed on this page. | |||
How do I use this page?
- Paste data and set α.
- Check the flagged value and G.
- Compare G with critical G and investigate the point's cause.
What this page does not do: The test assumes normal data and targets one outlier. Repeated testing after deletions changes the type-I error rate.
Further reading
Theory — what is the Grubbs test?
The Grubbs test checks the hypothesis that an approximately normal sample contains a single outlying value. The G statistic is the largest absolute distance of an observation from the mean divided by the standard deviation, compared against a critical value for the chosen significance level. Exceeding that critical value is only a statistical signal and does not automatically mean the point should be removed from the data.
Frequently asked questions
Does G above critical mean I must delete the point?
Can the test detect several points at once?
See also
A/B test calculator
Compare two proportions in an A/B test. Calculate conversion rates, difference, uplift, z score, p value and c
A/B test planning — sample size, MDE and duration
Plan a two-proportion experiment, estimate detectable effect and traffic duration.
ACF and PACF autocorrelation calculator
Calculate ACF and PACF across time-series lags. Review the chart, reference bounds and coefficient table.